Used np.vectorize to strip the excess string identfiers and switch from string check to integer check for counts.

thequackdaddy · thequackdaddy · commit dc5196a1884a · 2018-01-13T11:07:07.000-06:00
diff --git a/statsmodels/genmod/tests/results/results_glm.py b/statsmodels/genmod/tests/results/results_glm.py
@@ -684,7 +684,9 @@ def __init__(self):
         # data set up for data not in datasets
         filename = os.path.join(os.path.dirname(os.path.abspath(__file__)),
             "stata_lbw_glm.csv")
-        data=np.recfromcsv(open(filename, 'rb'), converters={4: lambda s: s.strip(asbytes("\""))})
+        data=np.recfromcsv(open(filename, 'rb'))
+        vfunc = np.vectorize(lambda x: x.strip(asbytes("\"")))
+        data['race'] = vfunc(data['race'])
         data = categorical(data, col='race', drop=True)
         self.endog = data.low
         design = np.column_stack((data['age'], data['lwt'],
@@ -2191,7 +2193,9 @@ class Medpar1(object):
     def __init__(self):
         filename = os.path.join(os.path.dirname(os.path.abspath(__file__)),
             "stata_medpar1_glm.csv")
-        data = np.recfromcsv(open(filename, 'rb'), converters ={1: lambda s: s.strip(asbytes("\""))})
+        data = np.recfromcsv(open(filename, 'rb'))
+        vfunc = np.vectorize(lambda x: x.strip(asbytes('\"')))
+        data['admitype'] = vfunc(data['admitype'])
         self.endog = data.los
         design = np.column_stack((data.admitype, data.codes))
         design = categorical(design, col=0, drop=True)
diff --git a/statsmodels/stats/tests/test_contingency_tables.py b/statsmodels/stats/tests/test_contingency_tables.py
@@ -61,7 +61,8 @@ def test_SquareTable_from_data():
                  rslt3.summary().as_text())
 
     s = str(rslt1)
-    assert_equal(s.startswith('A 5x5 contingency table with counts:\n[[ 8.'), True)
+    assert_equal(s.startswith('A 5x5 contingency table with counts:'), True)
+    assert_equal(rslt1.table[0, 0], 8.)
 
 
 def test_SquareTable_nonsquare():
